急性胆结石胰腺炎严重程度的早期预测:基于CT特征和开放式在线预测平台的新型机器学习模型
Yuhu Ma1, Ping Yue2, Jinduo Zhang2
1Department of Anesthesiology, The First Hospital of Lanzhou University, Lanzhou, Gansu, China.
Annals of medicine
|May 30, 2024
概括
胆结石胰腺炎的早期诊断 胆结石胰腺炎的严重程度通过新的ML GSP模型得到改善. 该模型使用临床和CT扫描功能来预测轻度或重度病例,提供更好的临床实用性.
科学领域:
- 放射学 放射学是一门学科.
- 医疗信息学 医疗信息学
- 胃肠病学 胃肠病学
背景情况:
- 准确的早期诊断急性胆结石胰腺炎严重程度 (GSP) 是临床上具有挑战性的.
- CT特征和放射学显示了早期GSP严重性预测的潜力.
研究的目的:
- 调查CT特征和放射性特征对急性GSP严重性早期预测的有效性.
- 开发和验证用于GSP严重性识别的机器学习 (ML) 模型.
主要方法:
- 在入院后48小时内接受CT成像检查的301名GSP患者的回顾性分析.
- 放射学和CT特征的提取;使用随机森林算法选择预测因素.
- 开发ML GSP模型并与放射学模型进行比较,以预测严重程度.
主要成果:
- ML GSP模型确定了七个预测因素:离子,白细胞计数,尿素水平,结合胆囊炎,胆囊壁加厚,胆结石和胸水.
- 在验证队列中,ML GSP模型实现了0.914的AUC,超过了放射学模型 (AUC0.841).
- ML GSP模型表现出良好的一致性和高临床效用.
结论:
- 一个新的ML GSP模型,结合临床和CT图像特征,有效预测GSP严重程度.
- 开发的模型可以作为免费的基于网络的计算器访问,增强临床决策.
更多相关视频
相关概念视频
Acute Pancreatitis II: Clinical Manifestations and Management
118
Acute pancreatitis presents a complex medical emergency characterized by rapid onset inflammation of the pancreas, demanding timely diagnosis and management to prevent complications. The condition primarily manifests through severe upper abdominal pain that often radiates to the back. This pain intensifies following the consumption of fatty foods. Accompanying symptoms such as nausea, vomiting, abdominal distention, fever, dyspnea, cyanosis, and jaundice can vary in intensity but significantly...
118
Chronic Pancreatitis II: Collaborative Care
84
The management of chronic pancreatitis is multifaceted, involving a comprehensive approach that includes thorough assessment, diagnostic testing, and a variety of management strategies.
Assessment:
Assessment:
84


